· Own the full deep learning model lifecycle, from data collection to deployment.
· Design and improve data collection, labeling, and annotation pipelines.
· Train, evaluate, and optimize detection, segmentation, keypoint, and tracking models.
· Develop synthetic datasets using Blender and Python-based rendering pipelines.
· Build and maintain reproducible MLOps pipelines, including experiment tracking and dataset versioning.
· Optimize models for deployment on embedded hardware.
· Define evaluation benchmarks and ensure model quality through automated testing.
· Collaborate with cross-functional teams to deliver production-ready AI solutions.